def main():
args = get_arguments()
data_train, data_test, charset = load_dataset(args.data)
model = MoleculeVAE()
if os.path.isfile(args.model):
model.load(charset, args.model, latent_rep_size=args.latent_dim)
else:
model.create(charset, latent_rep_size=args.latent_dim)
checkpointer = ModelCheckpoint(filepath=args.model,
verbose=1,
save_best_only=True)
reduce_lr = ReduceLROnPlateau(monitor='val_loss',
factor=0.2,
patience=3,
min_lr=0.0001)
model.autoencoder.fit(data_train,
data_train,
shuffle=True,
epochs=args.epochs,
batch_size=args.batch_size,
callbacks=[checkpointer, reduce_lr],
validation_data=(data_test, data_test))
def main():
args = get_arguments()
np.random.seed(args.random_seed)
from molecules.model import MoleculeVAE
from molecules.utils import one_hot_array, one_hot_index, from_one_hot_array, \
decode_smiles_from_indexes, load_dataset
from keras.callbacks import ModelCheckpoint, ReduceLROnPlateau
data_train, data_test, charset = load_dataset(args.data)
model = MoleculeVAE()
if os.path.isfile(args.model):
model.load(charset, args.model, latent_rep_size=args.latent_dim)
else:
model.create(charset, latent_rep_size=args.latent_dim)
checkpointer = ModelCheckpoint(filepath=args.model,
verbose=1,
save_best_only=True)
reduce_lr = ReduceLROnPlateau(monitor='val_loss',
factor=0.2,
patience=3,
min_lr=0.0001)
model.autoencoder.fit(data_train,
data_train,
shuffle=True,
epochs=args.epochs,
batch_size=args.batch_size,
callbacks=[checkpointer, reduce_lr],
validation_data=(data_test, data_test))
def main():
args = get_arguments()
np.random.seed(args.random_seed)
from molecules.model import MoleculeVAE
from molecules.utils import one_hot_array, one_hot_index, from_one_hot_array, \
decode_smiles_from_indexes, load_dataset
from keras.callbacks import ModelCheckpoint, ReduceLROnPlateau
data_train, data_test, charset = load_dataset(args.data)
model = MoleculeVAE()
if os.path.isfile(args.model):
model.load(charset, args.model, latent_rep_size = args.latent_dim)
else:
model.create(charset, latent_rep_size = args.latent_dim)
checkpointer = ModelCheckpoint(filepath = args.model,
verbose = 1,
save_best_only = True)
reduce_lr = ReduceLROnPlateau(monitor = 'val_loss',
factor = 0.2,
patience = 3,
min_lr = 0.0001)
model.autoencoder.fit(
data_train,
data_train,
shuffle = True,
nb_epoch = args.epochs,
batch_size = args.batch_size,
callbacks = [checkpointer, reduce_lr],
validation_data = (data_test, data_test)
)
def visualize_model(args):
model = MoleculeVAE()
data, charset = load_dataset(args.data, split = False)
if os.path.isfile(args.model):
model.load(charset, args.model)
else:
raise ValueError("Model file %s doesn't exist" % args.model)
plot(model.autoencoder, to_file = args.outfile)
def visualize_model(args):
model = MoleculeVAE()
data, charset = load_dataset(args.data, split = False)
if os.path.isfile(args.model):
model.load(charset, args.model)
else:
raise ValueError("Model file %s doesn't exist" % args.model)
plot(model.autoencoder, to_file = args.outfile)
def main():
args = get_arguments()
np.random.seed(args.random_seed)
from molecules.model import MoleculeVAE
from keras.callbacks import ModelCheckpoint, ReduceLROnPlateau
data = pd.read_hdf(args.data, 'table')
structures = data['structure']
# import gzip
# filepath = args.data
# structures = [line.split()[0].strip() for line in gzip.open(filepath) if line]
# can also use CanonicalSmilesDataGenerator
datobj = SmilesDataGenerator(structures, MAX_LEN,
test_split=args.test_split,
random_seed=args.random_seed)
test_divisor = int((1 - datobj.test_split) / (datobj.test_split))
train_gen = datobj.train_generator(args.batch_size)
test_gen = datobj.test_generator(args.batch_size)
# reformulate generators to not use weights
train_gen = ((tens, tens) for (tens, _, weights) in train_gen)
test_gen = ((tens, tens) for (tens, _, weights) in test_gen)
model = MoleculeVAE()
if os.path.isfile(args.model):
model.load(datobj.chars, args.model, latent_rep_size = args.latent_dim)
else:
model.create(datobj.chars, latent_rep_size = args.latent_dim)
checkpointer = ModelCheckpoint(filepath = args.model,
verbose = 1,
save_best_only = True)
reduce_lr = ReduceLROnPlateau(monitor = 'val_loss',
factor = 0.2,
patience = 3,
min_lr = 0.0001)
model.autoencoder.fit_generator(
train_gen,
args.epoch_size,
epochs = args.epochs,
callbacks = [checkpointer, reduce_lr],
validation_data = test_gen,
nb_val_samples = args.epoch_size / test_divisor,
pickle_safe = True
)
def main():
args = get_arguments()
np.random.seed(args.random_seed)
from molecules.model import MoleculeVAE
from keras.callbacks import ModelCheckpoint, ReduceLROnPlateau
data = pd.read_hdf(args.data, 'table')
structures = data['structure']
# import gzip
# filepath = args.data
# structures = [line.split()[0].strip() for line in gzip.open(filepath) if line]
# can also use CanonicalSmilesDataGenerator
datobj = SmilesDataGenerator(structures, MAX_LEN,
test_split=args.test_split,
random_seed=args.random_seed)
test_divisor = int((1 - datobj.test_split) / (datobj.test_split))
train_gen = datobj.train_generator(args.batch_size)
test_gen = datobj.test_generator(args.batch_size)
# reformulate generators to not use weights
train_gen = ((tens, tens) for (tens, _, weights) in train_gen)
test_gen = ((tens, tens) for (tens, _, weights) in test_gen)
model = MoleculeVAE()
if os.path.isfile(args.model):
model.load(datobj.chars, args.model, latent_rep_size = args.latent_dim)
else:
model.create(datobj.chars, latent_rep_size = args.latent_dim)
checkpointer = ModelCheckpoint(filepath = args.model,
verbose = 1,
save_best_only = True)
reduce_lr = ReduceLROnPlateau(monitor = 'val_loss',
factor = 0.2,
patience = 3,
min_lr = 0.0001)
model.autoencoder.fit_generator(
train_gen,
args.epoch_size,
nb_epoch = args.epochs,
callbacks = [checkpointer, reduce_lr],
validation_data = test_gen,
nb_val_samples = args.epoch_size / test_divisor,
pickle_safe = True
)
def main():
args = get_arguments()
if os.path.isfile(args.data):
h5f = h5py.File(args.data, 'r')
charset = list(h5f['charset'][:])
h5f.close()
else:
raise ValueError("Data file %s doesn't exist" % args.data)
model = MoleculeVAE()
if os.path.isfile(args.model):
model.load(charset, args.model, latent_rep_size = args.latent_dim)
else:
raise ValueError("Model file %s doesn't exist" % args.model)
results = interpolate(args.source, args.dest, args.steps, charset, model, args.latent_dim, args.width)
for result in results:
print(result[0], result[2])
def main():
args = get_arguments()
if os.path.isfile(args.data):
h5f = h5py.File(args.data, 'r')
charset = list(h5f['charset'][:])
h5f.close()
else:
raise ValueError("Data file %s doesn't exist" % args.data)
model = MoleculeVAE()
if os.path.isfile(args.model):
model.load(charset, args.model, latent_rep_size=args.latent_dim)
else:
raise ValueError("Model file %s doesn't exist" % args.model)
results = interpolate(args.source, args.dest, args.steps, charset, model,
args.latent_dim, args.width)
for result in results:
print(result[0], result[2])
def main():
args = get_arguments()
model = MoleculeVAE()
data, data_test, charset = load_dataset(args.data)
if os.path.isfile(args.model):
model.load(charset, args.model, latent_rep_size = args.latent_dim)
else:
raise ValueError("Model file %s doesn't exist" % args.model)
x_latent = model.encoder.predict(data)
if not args.visualize:
if not args.save_h5:
np.savetxt(sys.stdout, x_latent, delimiter = '\t')
else:
h5f = h5py.File(args.save_h5, 'w')
h5f.create_dataset('charset', data = charset)
h5f.create_dataset('latent_vectors', data = x_latent)
h5f.close()
else:
visualize_latent_rep(args, model, x_latent)
def main():
args = get_arguments()
model = MoleculeVAE()
data, data_test, charset = load_dataset(args.data)
if os.path.isfile(args.model):
model.load(charset, args.model, latent_rep_size=args.latent_dim)
else:
raise ValueError("Model file %s doesn't exist" % args.model)
x_latent = model.encoder.predict(data)
if not args.visualize:
if not args.save_h5:
np.savetxt(sys.stdout, x_latent, delimiter='\t')
else:
h5f = h5py.File(args.save_h5, 'w')
h5f.create_dataset('charset', data=charset)
h5f.create_dataset('latent_vectors', data=x_latent)
h5f.close()
else:
visualize_latent_rep(args, model, x_latent)